{"paper":{"title":"Learning to Theorize the World from Observation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A neural model learns to induce executable explanatory programs from raw observations alone.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Doojin Baek, Gyubin Lee, Hosung Lee, Junyeob Baek, Sungjin Ahn","submitted_at":"2026-05-05T06:39:12Z","abstract_excerpt":"What does it mean to understand the world? Contemporary world models often operationalize understanding as accurate future prediction in latent or observation space. Developmental cognitive science, however, suggests a different view: human understanding emerges through the construction of internal theories of how the world works, even before mature language is acquired. Inspired by this theory-building view of cognition, we introduce Learning-to-Theorize, a learning paradigm for inferring explicit explanatory theories of the world from raw, non-textual observations. We instantiate this paradi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments show that this formulation enables explanation-driven generalization, allowing observations to be understood in terms of the programs that generate them.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That raw non-textual observations alone suffice for a neural model to induce meaningful, compositional, and executable explanatory programs without additional structure or supervision.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"NEO induces compositional latent programs as world theories from observations and executes them to enable explanation-driven generalization.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A neural model learns to induce executable explanatory programs from raw observations alone.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f9a040f9410f5fdc6af76f81d4fb4ed221eb33b4cea053ba0327cad7eb65a000"},"source":{"id":"2605.03413","kind":"arxiv","version":2},"verdict":{"id":"c31c913f-c9bb-44ea-867c-e734ef0c0599","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T17:09:14.023811Z","strongest_claim":"Experiments show that this formulation enables explanation-driven generalization, allowing observations to be understood in terms of the programs that generate them.","one_line_summary":"NEO induces compositional latent programs as world theories from observations and executes them to enable explanation-driven generalization.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That raw non-textual observations alone suffice for a neural model to induce meaningful, compositional, and executable explanatory programs without additional structure or supervision.","pith_extraction_headline":"A neural model learns to induce executable explanatory programs from raw observations alone."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.03413/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T13:42:01.794331Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T01:01:22.166928Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:26:17.995734Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"f889794e65a78bd7df3e072013c6fab74be11fdcc839661f6e25042d3d5ab5f5"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}